-
Mathias Vast
- Team: MLIA
Publications
- Mihai Branga-Peicu, Mathias Vast, Basile van Cooten, Laure Soulier, Jules Françoise, et al.. IR Lens: A Tool for Interpreting Cross-Encoder Models. The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2026, Melbourne, Australia. pp.5135-5139, ⟨10.1145/3805712.3808382⟩. ⟨hal-05690304⟩
- Mathias Vast, Victor Morand, Basile van Cooten, Laure Soulier, Josiane Mothe, et al.. Encodeurs croisés légers pour ré-ordonner les résultats de recherche d'information. 21e Conférence en Recherche d’Information et Applications, Jun 2026, Nantes, France. pp.19-29. ⟨hal-05690307⟩
- Mathias Vast, Basile van Cooten, Laure Soulier, Benjamin Piwowarski. Understanding Matching Mechanisms in Cross-Encoders. Workshop on Explainability in Information Retrieval, Jul 2025, Padova, Italy, Italy. ⟨hal-05122957v2⟩
- Mathias Vast, Basile van Cooten, Laure Soulier, Benjamin Piwowarski. Comprendre la Nature des Signaux de Correspondance dans les Modèles Neuronaux pour la RI. Conférence en Recherche d’Information et Applications, Association francophone de Recherche d’Information et Applications, Jun 2025, Marseille, France. ⟨hal-05122843⟩
-
Mathias Vast, Basile van Cooten, Laure Soulier, Benjamin Piwowarski. Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-Encoders. ICTIR '24: The 2024 ACM SIGIR International Conference on the Theory of Information Retrieval, Jul 2024, Washington DC, United States. pp.133-143, ⟨10.1145/3664190.3672528⟩. ⟨hal-04668348⟩
[ HTTP ]
- Mathias Vast, Yuxuan Zong, Benjamin Piwowarski, Laure Soulier. Simple Domain Adaptation for Sparse Retrievers. 46th European Conference on Information Retrieval, Mar 2024, Glasgow, United Kingdom. pp.403-412, ⟨10.1007/978-3-031-56063-7_32⟩. ⟨hal-04517668⟩
